© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 52919
    Prev
    Next
    INDEX
    Explanations

    assistant refusal and safety-disclaimer responses to inappropriate, sexual, or illegal requests.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BarButtonItem
    -0.07
    MinMax
    -0.07
    _MATRIX
    -0.07
    是不可能
    -0.07
    ภาว
    -0.07
    ㇻ
    -0.07
    脍
    -0.07
    老旧小区
    -0.07
    咨
    -0.07
     brethren
    -0.07
    POSITIVE LOGITS
     plaint
    0.08
    〉
    0.07
     quis
    0.07
    灭亡
    0.07
    燃料
    0.06
     делать
    0.06
    깬
    0.06
     endforeach
    0.06
    ONSE
    0.06
    ItemList
    0.06
    Activations Density 0.104%

    No Known Activations